Pydoll MCP Server
pydoll-mcp
PyPI
v1.5.16
Published by jinsongroh — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 11 = 89. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
| ✓ | inspection depth (source) — how much of the target the scan could see |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 17
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: download_file → upload_file → execute_automation_script. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow download_file → upload_file → execute_automation_script
high Read-and-egress in one tool: "upload_file"MTC-FLOW-003
Tool "upload_file" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.
Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.
Location: flow upload_file
high Tool "execute_javascript" exposes command/code executionMTC-CAP-001
Tool "execute_javascript" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool execute_javascript
high Tool "execute_automation_script" exposes command/code executionMTC-CAP-001
Tool "execute_automation_script" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool execute_automation_script
high Shell/command execution in server code (publish.py)MTC-SRC-002
In the server's implementation (`publish.py:41`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server publish.py
high Shell/command execution in server code (pydoll_mcp/__main__.py)MTC-SRC-002
In the server's implementation (`pydoll_mcp/__main__.py:30`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server pydoll_mcp/__main__.py
high Shell/command execution in server code (pydoll_mcp/claude_setup.py)MTC-SRC-002
In the server's implementation (`pydoll_mcp/claude_setup.py:78`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server pydoll_mcp/claude_setup.py
high Shell/command execution in server code (pydoll_mcp/server.py)MTC-SRC-002
In the server's implementation (`pydoll_mcp/server.py:151`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server pydoll_mcp/server.py
medium Unconstrained URL/host parameter "url" on "download_file"MTC-CAP-007
Tool "download_file" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool download_file · inputSchema.properties.url
medium Unconstrained command parameter "script" on "execute_javascript"MTC-CAP-006
Tool "execute_javascript" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool execute_javascript · inputSchema.properties.script
medium Unconstrained command parameter "script_name" on "execute_automation_script"MTC-CAP-006
Tool "execute_automation_script" takes a command-shaped parameter "script_name" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool execute_automation_script · inputSchema.properties.script_name
medium Dynamic module load from a non-literal (pydoll_mcp/cli.py)MTC-SRC-005
In the server's implementation (`pydoll_mcp/cli.py:90`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: __import__(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server pydoll_mcp/cli.py
low Mutating tool "execute_javascript" declares no destructiveHintMTC-CAP-005
Tool "execute_javascript" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool execute_javascript
low Mutating tool "execute_automation_script" declares no destructiveHintMTC-CAP-005
Tool "execute_automation_script" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool execute_automation_script
low Unconstrained path parameter "file_path" on "upload_file"MTC-CAP-008
Tool "upload_file" takes a path parameter "file_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool upload_file · inputSchema.properties.file_path
low Unconstrained path parameter "save_path" on "download_file"MTC-CAP-008
Tool "download_file" takes a path parameter "save_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool download_file · inputSchema.properties.save_path
low Shell/command execution in packaging/dev tooling (tests/conftest.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/conftest.py:312`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/conftest.py
Tools 57
Each tool and what it can reach — statically extracted from the published source.
download_fileingests untrusted inputreads sensitive dataupload_filenetwork egressreads sensitive dataexecute_automation_scriptruns code / shellexecute_javascriptruns code / shellexport_to_csvnetwork egressexport_to_jsonnetwork egressfetch_domain_commandsingests untrusted inputget_page_sourceingests untrusted inputget_page_titleingests untrusted inputmodify_request_headersnetwork egressanalyze_content_with_aino sensitive capabilityanalyze_performanceno sensitive capabilityblock_requestsno sensitive capabilitybypass_cloudflareno sensitive capabilitybypass_recaptchano sensitive capabilitycheck_protection_statusno sensitive capabilityclear_cacheno sensitive capabilityclick_elementno sensitive capabilityclose_tabno sensitive capabilityenable_stealth_modeno sensitive capabilityevade_detectionno sensitive capabilityextract_api_responsesno sensitive capabilityextract_datano sensitive capabilityfind_elementno sensitive capabilitygenerate_pdfno sensitive capabilityget_browser_statusno sensitive capabilityget_current_urlno sensitive capabilityget_network_logsno sensitive capabilityget_parent_elementno sensitive capabilitygo_backno sensitive capabilityhandle_bot_detectionno sensitive capabilityinject_script_libraryno sensitive capabilityintelligent_searchno sensitive capabilityintercept_network_requestsno sensitive capabilitylist_browsersno sensitive capabilitylist_tabsno sensitive capabilityload_sessionno sensitive capabilitymanage_downloadsno sensitive capabilitymonitor_websocketsno sensitive capabilitynavigate_tono sensitive capabilitynew_tabno sensitive capabilityrandomize_fingerprintno sensitive capabilityrandomize_timingno sensitive capabilityrefresh_pageno sensitive capabilityrotate_proxyno sensitive capabilitysave_harno sensitive capabilitysave_sessionno sensitive capabilityset_active_tabno sensitive capabilityset_user_agentno sensitive capabilitysimulate_human_behaviorno sensitive capabilityspoof_headersno sensitive capabilitystart_browserno sensitive capabilitystop_browserno sensitive capabilitytake_element_screenshotno sensitive capabilitytake_screenshotno sensitive capabilitythrottle_networkno sensitive capabilitytype_textno sensitive capability
Toxic flows 2
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (57 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.5.16 latest |
B 89/100 | 17 | 1.8.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan pydoll-mcp --online --registry pypiMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Agent MCP server.